Ragas is the standard framework for measurable RAG evaluation: hallucination, faithfulness, relevancy
mdancho84 · x · 2026-09-19
The thread's #6 pick is Ragas, described as the standard framework for evaluating RAG pipelines — hallucination, faithfulness and relevancy are all measurable, and it can generate production-aligned test sets when you don't have one. The adjacent pick is Qdrant, a production vector database written in Rust (34.7k stars) that JDs list alongside Pinecone, Chroma, and FAISS.
Related event: Matt Dancho's 90-Day AI Engineer Roadmap: 10 GitHub Repos Over Courses(11 posts)→
More from coding & agent
- Orgo, a YC-backed platform giving AI agents their own cloud desktops, claims 1,000+ teams — Scobleizer · 2026-11-04
- Founder: Vibe-coded a PMF-successful product, then hired pro devs to fix the mess — sujingshen · 2026-11-04
- One prompt to audit cross-region traffic: dev cut trans-Atlantic latency by moving a service — DanielLockyer · 2026-11-04
- Agent silently completed only a quarter of a 200-module build and stalled waiting for confirmation — Promptmethus · 2026-11-04
- ChatGPT Agent mode can scan LinkedIn and Indeed and build a tailored job-application spreadsheet — nikola_mr64990 · 2026-11-04
- Blogger auto-applied to 500 jobs via ChatGPT and got 12 interview calls in 24 hours — nikola_mr64990 · 2026-11-04